© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 35799
    Prev
    Next
    INDEX
    Explanations

    Non-English Words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    徒
    -0.07
    47
    -0.06
     Hüs
    -0.06
    收益
    -0.06
    670
    -0.06
    Ş
    -0.06
    ENT
    -0.06
    SENT
    -0.06
    Hop
    -0.06
    checksum
    -0.06
    POSITIVE LOGITS
     seinen
    0.07
    相關
    0.06
    llu
    0.06
    .Variable
    0.06
     anno
    0.06
     bom
    0.06
     прос
    0.06
     nudity
    0.06
    :value
    0.06
     повинна
    0.06
    Activations Density 0.278%

    No Known Activations